Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    write something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    zerw
    0.39
    izou
    0.38
    ಲ್ಯ
    0.38
    quito
    0.38
     inferiore
    0.37
    保证金
    0.37
    innt
    0.36
    EDS
    0.36
     अग्
    0.36
    ِينَ
    0.36
    POSITIVE LOGITS
    巿
    0.42
     prést
    0.39
     оцен
    0.39
     coût
    0.38
     matériel
    0.38
     —,
    0.38
    ?”,
    0.37
     documental
    0.37
     dě
    0.37
     blogging
    0.37
    Act Density 0.000%

    No Known Activations